From 85a267daaa1c6f8fd69160445bcb88717031d10c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Johannes=20G=C3=A4=C3=9Fler?= <johannesg@5d6.de>
Date: Thu, 27 Jun 2024 16:26:05 +0200
Subject: [PATCH] CUDA: fix MMQ stream-k for --split-mode row (#8167)

---
 ggml/src/ggml-cuda/mmq.cuh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/ggml/src/ggml-cuda/mmq.cuh b/ggml/src/ggml-cuda/mmq.cuh
index 31fcbf139..1396e7a75 100644
--- a/ggml/src/ggml-cuda/mmq.cuh
+++ b/ggml/src/ggml-cuda/mmq.cuh
@@ -2475,7 +2475,7 @@ static void launch_mul_mat_q(ggml_backend_cuda_context & ctx, const mmq_args & a
 
     const dim3 block_nums_mmq(nsm, 1, 1);
 
-    ggml_cuda_pool & pool = ctx.pool();
+    ggml_cuda_pool & pool = ctx.pool(id);
     ggml_cuda_pool_alloc<float> tmp_fixup(pool, block_nums_mmq.x * mmq_x*mmq_y);
 
     if (args.ne01 % mmq_y == 0) {